Key facts
| API compatibility | OpenAI-compatible /v1/chat/completions (change the base URL) |
| Models | 30+ models from free to frontier tiers behind one API |
| Agent primitives | Function calling, JSON mode and streaming are live |
| Retrieval | Embeddings and RAG over your own corpus |
| Deployment | Plugsky cloud, VPC, on-prem or air-gapped |
| Pricing | Flat monthly self-serve plans with fair-use usage; see the live pricing page |
| Audio and images | Audio and image endpoints are coming soon — verify in the docs |
| Archive retrieval | Rights-aware metadata in your own collections |
TL;DR
- Keep your OpenAI SDK — change the base URL and model name.
- 30+ models behind one API, from free chat models to frontier reasoning.
- Deployment options from hosted cloud to VPC, on-prem and air-gapped.
- Keep rights and embargo metadata in your retrieval corpus.
- Editors approve; agents research and draft.
How it works, step by step
- Define the job, the permitted data sources and where a human must approve.
- Pilot archive search with rights metadata attached.
- Create a Plugsky account and generate an API key (free plan, no card required).
- Point your OpenAI SDK at the Plugsky base URL and map your model names.
- Index the approved corpus with embeddings and keep retrieval role-scoped.
- Keep publication behind editorial approval.
- Measure quality on your own samples, then scale with usage monitoring.
Try it yourself
Where AI agents pay off in media
Media teams do not lack ideas for agents; they lack a safe path from demo to production. The pattern below targets repetitive, document-heavy work where a human can check the output, which is where agents earn their place first. Treat the agent as a new team member with a narrow brief, explicit permissions and a probation period, and rollout becomes an operations exercise rather than a leap of faith.
- Story research — surface archive material and prior coverage with citations
- Archive search — answer natural-language questions across your back catalogue
- Metadata — draft tags, summaries and headlines for editor review
- Editorial QA — check copy against style guides and flag inconsistencies
A reference architecture for media agents
A research agent queries a scoped archive collection and returns sourced notes, while a metadata agent drafts tags and summaries into your CMS through tools. Editors approve everything that publishes, and rights checks stay with your team.
- Archive and style-guide retrieval collections
- Tools into CMS, DAM and asset systems
- Editorial approval before publication
- Rights and embargo flags carried through retrieval
Data governance and human oversight
Archive content carries rights, embargoes and sensitivity. Tag documents with those attributes, restrict retrieval accordingly, and keep a record of which sources informed each draft.
- Rights-aware retrieval metadata
- Editorial review before publication
- Audit logs for generated drafts
- AI-assisted work labelled per your policy
From pilot to production
Pilot archive search and research notes, then metadata drafting. Avoid automating publication until editorial review is tight and sources are traceable.
Keep the rollout reversible: run the agent in shadow mode alongside the current process, compare outputs on your own samples, and move it into the workflow only when the evidence holds. Document what you measured so expanding to the next team is a decision, not a hope.
Honest comparison
| Capability | Plugsky | Typical cloud AI API | Building in-house |
|---|---|---|---|
| API compatibility | Drop-in base URL change | Usually compatible | Full rewrite |
| Model access | 30+ models behind one API | Vendor's own catalogue | You host each model |
| Pricing | Flat monthly self-serve plans; see live pricing | Often per-token | GPU + ops cost |
| Deployment | Cloud, VPC, on-prem or air-gapped | Usually vendor cloud regions | You own the stack |
| Rights handling | You keep rights metadata; retrieval respects it | Varies | You build it |
| Audio workflows | Coming soon; use external transcription for now | Varies | You integrate |
Frequently asked questions
Do we have to rewrite our application?
No. The chat completions API is OpenAI-compatible, so you change the base URL and model name and keep your existing SDK.
Is there a free plan?
Yes — the free plan includes two free AI models, plugsky-micro and plugsky-lite, with no credit card required.
How is pricing structured?
Self-serve plans are flat monthly with fair-use usage and no per-token charges; see the live pricing page for current plans.
Which endpoints are live today?
Chat, streaming, JSON mode, function calling, embeddings, RAG and agents are live. Audio, images, moderation, files, batch, fine-tuning, assistants and responses endpoints are coming soon — check the docs before planning around them.
Can it transcribe interviews?
Audio endpoints are coming soon — check the docs for current status. Until then, use transcription tooling and pass the text to the API as context.
Will it surface copyrighted archive material?
Your archive is your corpus; retrieval does not change the rights attached to each item. Keep rights metadata in the collection and follow your own usage policy.
Can it write headlines?
It can draft options for editors to choose and refine; keep final editorial control with people.